aboutsummaryrefslogtreecommitdiff
path: root/net/ipv6/ip6_tunnel.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/ip6_tunnel.c')
-rw-r--r--net/ipv6/ip6_tunnel.c150
1 files changed, 93 insertions, 57 deletions
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index fff83cbc197..afa08245836 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -29,7 +29,6 @@
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
-#include <linux/if_tunnel.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
@@ -41,12 +40,14 @@
#include <linux/netfilter_ipv6.h>
#include <linux/slab.h>
#include <linux/hash.h>
+#include <linux/etherdevice.h>
#include <asm/uaccess.h>
#include <linux/atomic.h>
#include <net/icmp.h>
#include <net/ip.h>
+#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
@@ -60,6 +61,7 @@
MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("ip6tnl");
MODULE_ALIAS_NETDEV("ip6tnl0");
#ifdef IP6_TNL_DEBUG
@@ -68,9 +70,6 @@ MODULE_ALIAS_NETDEV("ip6tnl0");
#define IP6_TNL_TRACE(x...) do {;} while(0)
#endif
-#define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK)
-#define IPV6_TCLASS_SHIFT 20
-
#define HASH_SIZE_SHIFT 5
#define HASH_SIZE (1 << HASH_SIZE_SHIFT)
@@ -101,16 +100,26 @@ struct ip6_tnl_net {
static struct net_device_stats *ip6_get_stats(struct net_device *dev)
{
- struct pcpu_tstats sum = { 0 };
+ struct pcpu_sw_netstats tmp, sum = { 0 };
int i;
for_each_possible_cpu(i) {
- const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
-
- sum.rx_packets += tstats->rx_packets;
- sum.rx_bytes += tstats->rx_bytes;
- sum.tx_packets += tstats->tx_packets;
- sum.tx_bytes += tstats->tx_bytes;
+ unsigned int start;
+ const struct pcpu_sw_netstats *tstats =
+ per_cpu_ptr(dev->tstats, i);
+
+ do {
+ start = u64_stats_fetch_begin_irq(&tstats->syncp);
+ tmp.rx_packets = tstats->rx_packets;
+ tmp.rx_bytes = tstats->rx_bytes;
+ tmp.tx_packets = tstats->tx_packets;
+ tmp.tx_bytes = tstats->tx_bytes;
+ } while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
+
+ sum.rx_packets += tmp.rx_packets;
+ sum.rx_bytes += tmp.rx_bytes;
+ sum.tx_packets += tmp.tx_packets;
+ sum.tx_bytes += tmp.tx_bytes;
}
dev->stats.rx_packets = sum.rx_packets;
dev->stats.rx_bytes = sum.rx_bytes;
@@ -314,6 +323,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
t = netdev_priv(dev);
t->parms = *p;
+ t->net = dev_net(dev);
err = ip6_tnl_create2(dev);
if (err < 0)
goto failed_free;
@@ -373,7 +383,7 @@ static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
@@ -740,7 +750,7 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if ((p->flags & IP6_TNL_F_CAP_RCV) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
@@ -782,7 +792,7 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
&ipv6h->daddr)) != NULL) {
- struct pcpu_tstats *tstats;
+ struct pcpu_sw_netstats *tstats;
if (t->parms.proto != ipproto && t->parms.proto != 0) {
rcu_read_unlock();
@@ -799,14 +809,12 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
rcu_read_unlock();
goto discard;
}
- secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
skb->protocol = htons(protocol);
- skb->pkt_type = PACKET_HOST;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
- __skb_tunnel_rx(skb, t->dev);
+ __skb_tunnel_rx(skb, t->dev, t->net);
err = dscp_ecn_decapsulate(t, ipv6h, skb);
if (unlikely(err)) {
@@ -823,8 +831,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
}
tstats = this_cpu_ptr(t->dev->tstats);
+ u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ u64_stats_update_end(&tstats->syncp);
netif_rx(skb);
@@ -894,7 +904,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if (p->flags & IP6_TNL_F_CAP_XMIT) {
struct net_device *ldev = NULL;
@@ -944,8 +954,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
int encap_limit,
__u32 *pmtu)
{
- struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
+ struct net *net = t->net;
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
@@ -955,7 +965,6 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
unsigned int max_headroom = sizeof(struct ipv6hdr);
u8 proto;
int err = -1;
- int pkt_len;
if (!fl6->flowi6_mark)
dst = ip6_tnl_dst_check(t);
@@ -996,6 +1005,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
goto tx_err_dst_release;
}
+ skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
+
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
@@ -1013,7 +1024,6 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
consume_skb(skb);
skb = new_skb;
}
- skb_dst_drop(skb);
if (fl6->flowi6_mark) {
skb_dst_set(skb, dst);
ndst = NULL;
@@ -1027,6 +1037,12 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
init_tel_txopt(&opt, encap_limit);
ipv6_push_nfrag_opts(skb, &opt.ops, &proto, NULL);
}
+
+ if (likely(!skb->encapsulation)) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
+
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
@@ -1035,19 +1051,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
ipv6h->nexthdr = proto;
ipv6h->saddr = fl6->saddr;
ipv6h->daddr = fl6->daddr;
- nf_reset(skb);
- pkt_len = skb->len;
- err = ip6_local_out(skb);
-
- if (net_xmit_eval(err) == 0) {
- struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats);
-
- tstats->tx_bytes += pkt_len;
- tstats->tx_packets++;
- } else {
- stats->tx_errors++;
- stats->tx_aborted_errors++;
- }
+ ip6tunnel_xmit(skb, dev);
if (ndst)
ip6_tnl_dst_store(t, ndst);
return 0;
@@ -1136,7 +1140,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_TCLASS_MASK);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
- fl6.flowlabel |= (*(__be32 *) ipv6h & IPV6_FLOWLABEL_MASK);
+ fl6.flowlabel |= ip6_flowlabel(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
@@ -1214,7 +1218,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
- struct rt6_info *rt = rt6_lookup(dev_net(dev),
+ struct rt6_info *rt = rt6_lookup(t->net,
&p->raddr, &p->laddr,
p->link, strict);
@@ -1263,7 +1267,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
@@ -1337,8 +1341,8 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
int err = 0;
struct ip6_tnl_parm p;
struct __ip6_tnl_parm p1;
- struct ip6_tnl *t = NULL;
- struct net *net = dev_net(dev);
+ struct ip6_tnl *t = netdev_priv(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
switch (cmd) {
@@ -1350,11 +1354,11 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
}
ip6_tnl_parm_from_user(&p1, &p);
t = ip6_tnl_locate(net, &p1, 0);
+ if (t == NULL)
+ t = netdev_priv(dev);
} else {
memset(&p, 0, sizeof(p));
}
- if (t == NULL)
- t = netdev_priv(dev);
ip6_tnl_parm_to_user(&p, &t->parms);
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof (p))) {
err = -EFAULT;
@@ -1435,9 +1439,17 @@ ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
static int
ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
{
- if (new_mtu < IPV6_MIN_MTU) {
- return -EINVAL;
+ struct ip6_tnl *tnl = netdev_priv(dev);
+
+ if (tnl->parms.proto == IPPROTO_IPIP) {
+ if (new_mtu < 68)
+ return -EINVAL;
+ } else {
+ if (new_mtu < IPV6_MIN_MTU)
+ return -EINVAL;
}
+ if (new_mtu > 0xFFF8 - dev->hard_header_len)
+ return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
@@ -1475,8 +1487,10 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
dev->mtu-=8;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ /* This perm addr will be used as interface identifier by IPv6 */
+ dev->addr_assign_type = NET_ADDR_RANDOM;
+ eth_random_addr(dev->perm_addr);
}
@@ -1491,7 +1505,8 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
- dev->tstats = alloc_percpu(struct pcpu_tstats);
+ t->net = dev_net(dev);
+ dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
@@ -1543,7 +1558,7 @@ static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[])
{
u8 proto;
- if (!data)
+ if (!data || !data[IFLA_IPTUN_PROTO])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
@@ -1608,9 +1623,9 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip6_tnl *t;
+ struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm p;
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
@@ -1629,6 +1644,15 @@ static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
return ip6_tnl_update(t, &p);
}
+static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
+{
+ struct net *net = dev_net(dev);
+ struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+
+ if (dev != ip6n->fb_tnl_dev)
+ unregister_netdevice_queue(dev, head);
+}
+
static size_t ip6_tnl_get_size(const struct net_device *dev)
{
return
@@ -1658,9 +1682,9 @@ static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
nla_put(skb, IFLA_IPTUN_LOCAL, sizeof(struct in6_addr),
- &parm->raddr) ||
- nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
&parm->laddr) ||
+ nla_put(skb, IFLA_IPTUN_REMOTE, sizeof(struct in6_addr),
+ &parm->raddr) ||
nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
@@ -1693,6 +1717,7 @@ static struct rtnl_link_ops ip6_link_ops __read_mostly = {
.validate = ip6_tnl_validate,
.newlink = ip6_tnl_newlink,
.changelink = ip6_tnl_changelink,
+ .dellink = ip6_tnl_dellink,
.get_size = ip6_tnl_get_size,
.fill_info = ip6_tnl_fill_info,
};
@@ -1709,22 +1734,30 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
.priority = 1,
};
-static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
+static void __net_exit ip6_tnl_destroy_tunnels(struct net *net)
{
+ struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ struct net_device *dev, *aux;
int h;
struct ip6_tnl *t;
LIST_HEAD(list);
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == &ip6_link_ops)
+ unregister_netdevice_queue(dev, &list);
+
for (h = 0; h < HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
- unregister_netdevice_queue(t->dev, &list);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, &list);
t = rtnl_dereference(t->next);
}
}
- t = rtnl_dereference(ip6n->tnls_wc[0]);
- unregister_netdevice_queue(t->dev, &list);
unregister_netdevice_many(&list);
}
@@ -1744,6 +1777,11 @@ static int __net_init ip6_tnl_init_net(struct net *net)
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
+ ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops;
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
@@ -1766,10 +1804,8 @@ err_alloc_dev:
static void __net_exit ip6_tnl_exit_net(struct net *net)
{
- struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
-
rtnl_lock();
- ip6_tnl_destroy_tunnels(ip6n);
+ ip6_tnl_destroy_tunnels(net);
rtnl_unlock();
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 03:57:57 +0000